search

LiyuanLucasLiu / LD-Net

Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
https://arxiv.org/abs/1804.07827
Apache License 2.0
146 stars 13 forks source link

MUC-7 Support #14

Open loretoparisi opened 5 years ago

loretoparisi commented 5 years ago

Currently, CoreNLP NER supports from 3 classes CoNLL to the MUC-7 classes, depending on the model loaded in the CoreNLP pipeline:

# tags: LOCATION, ORGANIZATION, PERSON
edu/stanford/nlp/models/ner/english.all.3class.distsim.crf.ser.gz
# tags: DATE, LOCATION, MONEY, ORGANIZATION, PERCENT, PERSON, TIME
edu/stanford/nlp/models/ner/english.muc.7class.distsim.crf.ser.gz
# LOCATION, MISC, ORGANIZATION, PERSON
edu/stanford/nlp/models/ner/english.conll.4class.distsim.crf.ser.gz

They can also be combine all together to obtain the 7 classes output CFR predictor. It would be possible to support the MUC-7 classes?

Thank you.

LiyuanLucasLiu commented 5 years ago

Thanks for asking! We do have plan to train more models and release in the future :-) For now, I think you can first try to train the model by yourself (I'm currently focusing on some other projects). Also, you are welcome to submit a PR!